mlsanityData to 14 Oct 2026

RObotic MAnipulation Network (ROMAN) -- Hybrid Hierarchical Learning for Solving Complex Sequential Tasks

arXiv 2307.00125 ↗First posted 30 Jun 2023cs.RO cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Solving long sequential tasks poses a significant challenge in embodied artificial intelligence. Enabling a robotic system to perform diverse sequential tasks with a broad range of manipulation skills is an active area of research. In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation. ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. It consists of a central manipulation network that coordinates an ensemble of various neural networks, each specialising in distinct re-combinable sub-tasks to generate their correct in-sequence actions for solving complex long-horizon manipulation tasks. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks and achieving adaptive behaviours beyond demonstrations, while exhibiting robustness to various sensory noises. These results demonstrate the significance and versatility of ROMAN's dynamic adaptability featuring autonomous failure recovery capabilities, and highlight its potential for various autonomous manipulation tasks that demand adaptive motor skills.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 31 of its 61 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

31 of 61 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division28 Mar

Other references · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2015Trust Region Policy Optimizationcited by 2,580
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  5. 2016Generative Adversarial Imitation Learningcited by 1,597
  6. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  7. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  8. 2018Learning Dexterous In-Hand Manipulationcited by 687
  9. 2018Behavioral Cloning from Observationcited by 492
  10. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  11. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  12. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
18 more
  1. 2018Unity: A General Platform for Intelligent Agentscited by 236
  2. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 217
  3. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  4. 2019Goal-conditioned Imitation Learningcited by 162
  5. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  6. 2019MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policiescited by 108
  7. 2017Meta Learning Shared Hierarchiescited by 93
  8. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
  9. 2020Multi-expert learning of adaptive legged locomotioncited by 67
  10. 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 64
  11. 2017Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learningcited by 40
  12. 2018Hierarchical visuomotor control of humanoidscited by 30
  13. 2018Learning from Demonstration in the Wildcited by 25
  14. 2021Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtaskscited by 14
  15. 2021Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulationcited by 13
  16. 2021Versatile modular neural locomotion control with fast learningcited by 6
  17. 2021Metrics for 3D Object Pointing and Manipulation in Virtual Realitycited by 2
  18. 2021The Challenges in Modeling Human Performance in 3D Space with Fitts' Lawcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
  2. 2026ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning
  3. 2025SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation
  4. 2026Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation
  5. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery
  6. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
  7. 2025Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
  8. 2026RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation